huangyanpei/VLA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix tokenizer reading and update README

Browse Source
This commit is contained in:
Starrick
2025-09-09 16:35:05 +08:00
parent f1a9567f61
commit d9305278af
3 changed files with 10 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
workspace/README.md
+3 -3
View File
@@ -19,10 +19,10 @@ git clone https://huggingface.co/physical-intelligence/fast
## Required Paths (Must Modify)
```yaml
pretrained_wallx_path: "/path/to/wallx_model/" # Path to pretrained Qwen VL model
use_fast_tokenizer: false # True: train FAST, False: train Flow
action_tokenizer_path: "/path/to/fast/" # Path to action tokenizer
pretrained_wallx_path: "/path/to/wallx_model/" # Path to pretrained wallx model
save_path: "/path/to/workspace/" # Path to save training outputs
use_fast_tokenizer: False # True: train FAST, False: train Flow
action_tokenizer_path: "/path/to/fast/" # Must set if use_fast_tokenizer is True
```
## Training Parameters (Commonly Modified)
workspace/lerobot_example/config_qact.yml
+4 -4
View File
@@ -5,10 +5,10 @@
log_name: "robotic_training"
log_project: "vla_training"
model_type: qwen2_5
pretrained_wallx_path: "/path/to/wallx_model/"
use_fast_tokenizer: false # True: train FAST, False: train Flow
action_tokenizer_path: "/path/to/fast/"
save_path: "/path/to/workspace/"
pretrained_wallx_path: "/path/to/wallx_model/" # Must set
save_path: "/path/to/workspace/" # Must set
use_fast_tokenizer: False # True: train FAST, False: train Flow
action_tokenizer_path: "/path/to/fast/" # Must set if use_fast_tokenizer is true
# Torch Profile
profile: False